SBM11: Sketch Based Interfaces and Modeling 2011
Permanent URI for this collection
Browse
Browsing SBM11: Sketch Based Interfaces and Modeling 2011 by Issue Date
Now showing 1 - 18 of 18
Results Per Page
Sort Options
Item Neatening sketched strokes using piecewise French Curves(The Eurographics Association, 2011) McCrae, James; Singh, Karan; Tracy Hammond and Andy NealenWe apply traditional bimanual curve modeling using French curves to the problem of automatic neatening of sketched strokes. Given a sketched input stroke and a set of template French curves we present an approach that fits the stroke using an optimal number of French curve segments. Our algorithm operates in both curvature andpoint space, reconstructing the salient curvature profiles of French curve segments, while limiting error accumulation resulting from curvature integration. User-controlled parameters allow the neatened stroke to model G2 continuous curves, capture G1 discontinuities, define closed curves and explore the trade-off between fitting errorand the number of French curve segments used. We present an interactive sketch stroke neatening implementation to demonstrate the real-time performance of our algorithm and evaluate the quality of its results.Item Combining Corners from Multiple Segmenters(The Eurographics Association, 2011) Wolin, Aaron; Field, Martin; Hammond, Tracy; Tracy Hammond and Andy NealenPen-based interfaces utilize sketch recognition in order to allow users to sketch complex systems with intuitive input. In order to allow users to freely draw their ideas without constraints, the low-level techniques involved with sketch recognition must be perfected because poor low-level accuracy can impair a user s interaction experience. Stroke segmentation algorithms often employ single, specific techniques in their attempts to splice strokes into primitives used for visual shape representations. These algorithms each have their strengths and weaknesses, and different segmenters find and miss different corners. We introduce a technique to combine polyline corner results from different segmenters by using a variation offeature subset selection. Our feature subset selection algorithm uses a sequential floating backward selection with a mean-squared error objective function in order to find the best subset of corners. By utilizing our combination method, we were able to achieve all-or-nothing accuracies of 0.926 on polyline stroke data.Item Continuous Recognition and Visualization of Pen Strokes and Touch-Screen Gestures(The Eurographics Association, 2011) Kristensson, P.O.; Denby, L.C.; Tracy Hammond and Andy NealenWe present a technique that enables continuous recognition and visualization of pen strokes and touch-screen gestures. We describe an incremental recognition algorithm that provides probability distributions over template classes as a function of users partial or complete stroke articulations. We show that this algorithm can predictusers intended template classes with high accuracy on several different datasets. We use the algorithm to design two new visualizations that reveal various aspects of the recognition process to users. We then demonstrate how these visualizations can help users to understand how the recognition process interprets their input and how interactions between different template classes affect recognition outcomes.Item Sketch Express: Facial Expressions Made Easy(The Eurographics Association, 2011) Miranda, José Carlos; Alvarez, Xenxo; Orvalho, João; Gutierrez, Diego; Sousa, A. Augusto; Orvalho, Verónica; Tracy Hammond and Andy NealenFinding an effective control interface to manipulate complex eometric objects has traditionally relied on experienced users to place the animation controls. This process, whether for key framed or for motion captured animation, takes a lot of time and effort. We introduce a novel sketching interface control system inspired in theway artists draw, in which a stroke defines the shape of an object and reflects the user s intention. We also introduce the canvas, a 2D drawing region where the users can make their strokes, which determines the domain of interaction with the object. We show that the combination of strokes and canvases provides a new way to manipulate the shape of an implicit volume in space. And most importantly, it is independent from the 3D model rig. The strokes can be easily stored and reused in other characters, allowing retargeting of poses. Our interactive approach is illustrated using facial models of different styles. As a result, we allow rapid manipulation of 3D faceson the fly in a very intuitive and interactive way. Our informal study showed that first time users typically master the system within seconds, creating appealing 3D poses and animations in just a few minutes.Item A Sketch-Based System for Highway Design(The Eurographics Association, 2011) Applegate, C. S.; Laycock, S. D.; Day, A. M.; Tracy Hammond and Andy NealenTo create traffic simulations of high visual-fidelity, each road needs to be designed and modelled in great detail to conform with the governing rules and regulations of highway design. Roads could be created manually, but this can become a time-consuming and laborious process when modelling large-scale networks. Therefore, automated techniques for generating road networks efficiently and effectively, without any prior user knowledge of road design principles and practices, is highly desirable in both urban-planning and entertainment industries. In this paper, we present a novel sketch-based tool to semi-automate the design, creation and visualisation of realistic road networks across both flat and undulating terrains. Our tool is guided by input sketches and a combination of prioritised constraints, including the curvature of roads, their inclination, and the volume of ground that wouldbe displaced during construction. Furthermore, we present an extension to a cellular automata traffic behaviour model that utilises more accurate car-following rules to simulate large-scale networks with high visual-fidelity.Item Sketch-Based Modeling of Smooth Surfaces Using AdaptiveCurve Networks(The Eurographics Association, 2011) Orbay, Günay; Kara, Levent Burak; Tracy Hammond and Andy NealenWe present a new 3D surface modeling method that enables a rapid creation and modification of globally smooth surfaces from curve networks. The key feature of the proposed method is that it assumes the sketched curve networks to be malleable rather than rigid, thus enabling a mediation between curve interpolation versus surfacesmoothness. In the first step, the user sketches a network topology in the form of cubic feature edges. The curve network serves as an initial control mesh, from which a subdivision surface is computed. The subdivision surface is then iteratively modified to make the limit surface interpolate the original curve network at an arbitrary numberof points, while minimizing the curvature variation energy of the surface. For networks in which this forced interpolation causes undesirable distortions to the surface, the network is automatically adjusted to make it conform to a smoothed version of the surface. This approach enables a concurrent modeling of the curve network and the underlying surface, thus eliminating the need for a laborious, iterative adjustment of the curve network for smoothsurface creationItem StereoBrush: Interactive 2D to 3D Conversion UsingDiscontinuous Warps(The Eurographics Association, 2011) Wang, O.; Lang, M.; Frei, M.; Hornung, A.; Smolic, A.; Gross, M.; Tracy Hammond and Andy NealenWe introduce a novel workflow for stereoscopic 2D to 3D conversion in which the user “paints” depth onto a 2D image via sparse scribbles, instantaneously receiving intuitive 3D feedback. This workflow is enabled by the introduction of a discontinuous warping technique that creates stereoscopic pairs from sparse, possibly erroneous user input. Our method assumes a piecewise continuous depth representation, preserving visual continuity in most areas, while creating sharp depth discontinuities at important object boundaries. As opposed to prior work thatrelies strictly on a per pixel depth map, our scribbles are processed as soft constraints in a global solve and operate entirely on image domain disparity, allowing for relaxed input requirements. This formulation also allows us to simultaneously compute a disparity-and-content-aware stretching of background areas to automatically fill disoccluded regions with valid stereo information. We tightly integrate all steps of stereo content conversion into a single optimization framework, which can then be solved on a GPU at interactive rates. The instant feedback received while painting depth allows even untrained users to quickly create compelling 3D scenes from single-view footage.Item Reconstructing surfaces from sketched 3D irregular curvenetworks(The Eurographics Association, 2011) Morigi, S.; Rucci, M.; Tracy Hammond and Andy NealenThis paper presents a system for designing free-form surfaces starting from a sketched 3D irregular curve network. By simply dragging a smart-pen device in space, the user draws and refines arbitrary 3D style-curves that define an outline of the desired shape. Unlike previous touch-based sketching systems, the user-drawn strokes can both stay on the model surface to reconstruct parts of an existing object, or freely sketch 3D style-lines of non-existingparts to design new geometry. The wireless smart-pen device is supported by an active stereo acquisition system which makes use of two infrared cameras. For a given set of 3D curves, the system automatically constructs a lowresolution mesh that is naturally refined to produce a smooth surface which preserves curvature features defined by the user on the curve network. The interpolating surface is obtained by applying a high-order diffusion flow. We present an efficient two step approach that first diffuses curvature values preserving the curvature constraints, and then corrects the surface to fit the resulting curvature vector field and interpolating the 3D curve network. This leads to fast implementation of a feature preserving fourth order geometric flow. We show several examplesto demonstrate the ability of the proposed advanced design methodology to create sophisticated models possibly having sharp creases and corners.Item Is the iPad useful for sketch input? A comparison with the Tablet PC(The Eurographics Association, 2011) MacLean, S.; Tausky, D.; Labahn, G.; Lank, E.; Marzouk, M.; Tracy Hammond and Andy NealenDespite the increasing prevalence of touch-based tablet devices, little attention has been paid to what effects, if any, this form factor has on sketch behaviours in general and on sketch recognizers in particular.We investigate the title question through an empirical study in the context of mathematical expression recognition. Using a corpus of thirty expressions drawn on Tablet PC and iPad by thirty writers, we show that characteristics of sketching and drawingdiffer depending on platform. While recognition is most accurate on the Tablet PC due to its technical superiority, recognition is feasible on mobile touch-based devices. However, there are characteristics of sketching on multitouch tablets that differ, and these physical characteristics of writing impact recognition accuracy. Together, ourobservations inform the broader Sketch Recognition community as they design systems targeted to multi-touch tablets.Item Immersion and Embedding of Self-Crossing Loops(The Eurographics Association, 2011) Mukherjee, Uddipan; M.Gopi,; Rossignac, Jarek; Tracy Hammond and Andy NealenThe process of generating a 3D model from a set of 2D planar curves is complex due to the existence of many solutions. In this paper we consider a self-intersecting planar closed loop curve, and determine the 3D layered surface P with the curve as its boundary. Specifically, we are interested in a particular class of closed loop curvesin 2D with multiple self-crossings which bound a surface homeomorphic to a topological disk. Given such a selfcrossingclosed loop curve in 2D, we find the deformation of the topological disk whose boundary is the given loop. Further, we find the surface in 3D whose orthographic projection is the computed deformed disk, thus assigning 3D coordinates for the points in the self-crossing loop and its interior space.We also make theoretical observationsas to when, given a topological disk in 2D, the computed 3D surface will self-intersect.Item How to make a Quick$: Using Hierarchical Clustering toImprove the Efficiency of the Dollar Recognizer(The Eurographics Association, 2011) Reaver, J.; Stahovich, T. F.; Herold, J.; Tracy Hammond and Andy NealenWe present Quick$ (QuickBuck), an extension to the Dollar Recognizer designed to improve recognition efficiency. While the Dollar Recognizer must search all training templates to recognize an unknown symbol, Quick$ employs hierarchical clustering along with branch and bound search to do this more efficiently. Experiments have demonstrated that Quick$ is almost always faster than the Dollar Recognizer and always selects the same best-match templates.Item Defining Precise Measurements with Sketched Annotations(The Eurographics Association, 2011) Kebodeaux, Kourtney; Field, Martin; Hammond, Tracy; Tracy Hammond and Andy NealenTechnology has been largely employed in the modern education system but rarely fosters natural communication between the human and the machine. We wish to explore the use of sketch recognition based software as a medium for student computer interaction within the context of computer assisted tutoring systems. Since the student can draw directly on the screen in this scenario, the interaction mimics familiar pencil and paper techniques while the speed and one-on-one attention of the computer alleviate some of the challenges currently faced by students and teachers in a traditional education setting. Furthermore, we wish to promote the incorporation of more free response questions ( build a structure to meet these requirements instead of analyze this structure ) into the modern curriculum. These types of questions are rare because of how difficult they are to grade, but more closely approximate reality and provide context for the ethodologies learned in the classroom. Free response questions require a large degree of flexibility and an overall more intelligent tutoring system than has been previously studied. Mechanix is a sketch recognition based tutoring system that provides immediate feedback for engineering statics problems. In order to extend Mechanix to support free response problems, the software needs to know the precise physical properties of sketched elements. We ntroduce measurement mechanisms such that, with minimal effort, a user may specify the precise measurements of a truss, so that Mechanix can create and solve systems of equations to determine how forces are distributed throughout the truss. Therefore, given a sketched truss and measurements as a response to a free response questions, the system may determine whether the structure satisfies the requirements of the question.Item Combining bimanual manipulation and pen-based inputfor 3D modelling(The Eurographics Association, 2011) Lopes, Pedro; Mendes, Daniel; Araújo, Bruno; Jorge, Joaquim A.; Tracy Hammond and Andy NealenMultitouch enabled surfaces can bring advantages to modelling scenarios, in particular if bimanual and pen input can be combined. In this work, we assess the suitability of multitouch interfaces to 3D sketching tasks. We developed a multitouch enabled version of ShapeShop, whereby bimanual gestures allow users to explorethe canvas through camera operations while using a pen to sketch. This provides a comfortable setting familiar to most users. Our contribution focuses on comparing the combined approach (bimanual and pen) to the penonly interface for similar tasks. We conducted the evaluation helped by ten sketching experts who exercised both techniques. Results show that our approach both simplifies workflow and lowers task times, when compared to thepen-only interface, which is what most current sketching applications provide.Item ClassySeg: A Machine Learning Approach to AutomaticStroke Segmentation(The Eurographics Association, 2011) Herold, J.; Stahovich, T. F.; Tracy Hammond and Andy NealenWe present ClassySeg, a technique for segmenting hand-drawn pen strokes into lines and arcs. ClassySeg employs machine learning techniques to infer the segmentation intended by the drawer. The technique begins by identifying a set of candidate segment points, consisting of all curvature maxima. Features are computed for each candidate point based on speed, curvature, and other geometric properties. These features are adapted from numerous prior segmentation approaches, effectively combining their strengths. These features are used to train a statistical classifier to identify which candidate points are true segment points. A beam search is used to approximate the optimal subset of features to use as input to the classifier. ClassySeg is more accurate than previous techniques foruser-independent training conditions, and is as good as the current state-of-the-art algorithm for user-optimized conditions. More importantly, ClassySeg represents a movement away from prior heuristic-based approaches towards a more general and extensible approach.Item Single-View Sketch Based Modeling(The Eurographics Association, 2011) Andre, Alexis; Saito, Suguru; Tracy Hammond and Andy NealenThis paper presents a new sketch modeling system that is able to generate complex objects drawn from a unique viewpoint. The user draws the model in an iterative manner, adding simple parts to the existing object until completion. Each part is constructed from two construction lines (lines on the surface of the object that are planarand perpendicular to each other) whose orientation in the 3D space is uniquely determined by the system, and an optional silhouette. The system is then able to produce rough 3D reconstructions of drawings very easily by tracing over a sketch for example. Such models are perfectly suited to investigate their shade or shadow and theycan be used as substitutes for more detailed models when the need for quick models is present. The user can also explore shapes directly on the system, refining the shape on the go in a oversketching way. The creation of models is very efficient, as the user models the shapes directly in the correct pose and orientation. Results show that the system is able to create complex objects without ever having to change the viewpointItem 3D Modeling with a Symmetric Sketch(The Eurographics Association, 2011) Öztireli, A. C.; Uyumaz, U.; Popa, T.; Sheffer, A.; Gross, M.; Tracy Hammond and Andy NealenWe propose a method that allows geometric operations such as view change, deformation, simulation, or symmetrization on a single off-line sketch via a proxy geometry reconstructed directly from the sketch. The reconstruction captures the overall shape of the object depicted by making use of the global relationships of the curvesand the assumption that the sketched object is bilaterally symmetric. After cleaning the sketch and extracting the curves, topological and geometric properties of a set of identified points are used to derive robust correspondence and pairwise constraints. These constraints are considered all at once in a spectral algorithm to get the optimummatching of the curves. Depths of points on the matched curves are extracted by utilizing the symmetry assumption. They are then used to reconstruct a smooth geometry. The whole process is automatic except for a few seconds of user interaction.Item Now or Later: An Initial Exploration into User Perception ofMathematical Expression Recognition Feedback(The Eurographics Association, 2011) Bott, Jared N.; Gabriele, Daniel; Jr., Joseph J. LaViola; Tracy Hammond and Andy NealenMathematical handwriting recognition is an important method of mathematics input for computers. While strides in recognition have been made in recent years, recognition is still at a level where mistakes are common and often inexplicable from the user s point-of-view. As a result, recognition mistakes can cause user distraction andfrustration. We examine how user preference for real-time or batch recognition mode is affected by recognition accuracy and the number of expressions entered. Our results show that users prefer real-time recognition when working with multiple expressions; however, with high accuracy recognition, users did not prefer one recognitionmode over the other.Item Gesture-based design of 2D contours: an alternative tosketching?(The Eurographics Association, 2011) Delamé, T.; Léon, J.C.; Cani, M.P.; Blanch, R.; Tracy Hammond and Andy NealenIn addition to being a very expressive media, 2D sketches representing the contour of a shape are commonly used as a basis for 3D sketch-based modeling. This paper investigates an alternative to the standard way of creating such sketches: instead of carefully following the contour with a pen and erasing or over-sketching, theuser progressively shapes the contour from a simple input curve, only through intuitive deformation gestures. No menus or sliders are used. This is achieved by providing an automatic selection mechanism between a minimal set of deformation operators, inspired from Michael Leyton s perceptual theory of shapes. The shape representation and the active operator parameters are kept transparent to the user. This enables user to focus on the designand makes the system immediately usable by anybody. We validate this new paradigm through a user study that includes a comparison with standard sketching.